Predicting Non-Small-Cell Lung Cancer Survival after Curative Surgery via Deep Learning of Diffusion MRI.

BACKGROUND: the objective of this study is to evaluate the predictive power of the survival model using deep learning of diffusion-weighted images (DWI) in patients with non-small-cell lung cancer (NSCLC). METHODS: DWI at b-values of 0, 100, and 700 sec/mm2 (DWI0, DWI100, DWI700) were preoperatively obtained for 100 NSCLC patients who underwent curative surgery (57 men, 43 women; mean age, 62 years). The ADC0-100 (perfusion-sensitive ADC), ADC100-700 (perfusion-insensitive ADC), ADC0-100-700, and demographic features were collected as input data and 5-year survival was collected as output data. Our survival model adopted transfer learning from a pre-trained VGG-16 network, whereby the softmax layer was replaced with the binary classification layer for the prediction of 5-year survival. Three channels of input data were selected in combination out of DWIs and ADC images and their accuracies and AUCs were compared for the best performance during 10-fold cross validation. RESULTS: 66 patients survived, and 34 patients died. The predictive performance was the best in the following combination: DWI0-ADC0-100-ADC0-100-700 (accuracy: 92%; AUC: 0.904). This was followed by DWI0-DWI700-ADC0-100-700, DWI0-DWI100-DWI700, and DWI0-DWI0-DWI0 (accuracy: 91%, 81%, 76%; AUC: 0.889, 0.763, 0.711, respectively). Survival prediction models trained with ADC performed significantly better than the one trained with DWI only (p-values < 0.05). The survival prediction was improved when demographic features were added to the model with only DWIs, but the benefit of clinical information was not prominent when added to the best performing model using both DWI and ADC. CONCLUSIONS: Deep learning may play a role in the survival prediction of lung cancer. The performance of learning can be enhanced by inputting precedented, proven functional parameters of the ADC instead of the original data of DWIs only.

Preoperative Helical Dynamic Enhanced Multidetector Row Computed Tomography: Can It Be a Prognostic Indicator in Early-Stage Non-small Cell Lung Cancer?

OBJECTIVE: This study aimed to investigate the prognostic significance of dynamic contrast-enhanced computed tomography in patients with stage IA non-small cell lung cancer (NSCLC). METHODS: We retrospectively enrolled 139 patients (77 men, 62 women; mean age, 59 years) with stage IA NSCLC who underwent dynamic contrast-enhanced computed tomography. Data on age, pathologic subtype, peak enhancement, and net enhancement of primary lung cancer were collected and correlated with 5-year survival. RESULTS: Peak enhancement had a significant correlation with overall survival in the univariable analysis (hazard ratio [HR], 1.18, confidence interval [CI], 1.01-1.38; P = 0.04) and in the multivariable analysis (HR, 1.19; CI, 1.01-1.39; P = 0.04). Patients with peak enhancement of 90 Hounsfield unit or higher had a significantly increased risk of death compared with patients with less enhancement after curative surgery (HR, 4.15; CI, 1.23-13.95; P = 0.02). CONCLUSIONS: Our study confirmed the prognostic significance of peak enhancement as an indicator for the overall survival of stage IA NSCLC.

Dynamic contrast-enhanced MRI for response evaluation of non-small cell lung cancer in therapy with epidermal growth factor receptor tyrosine kinase inhibitors: a pilot study.

BACKGROUND: It is important to identify candidates who would benefit from target agent chemotherapy in advanced NSCLC patients. The purpose of this study is to evaluate the feasibility of DCE-MRI for early response evaluation in epidermal growth factor receptor (EGFR) tyrosine kinase inhibitors (TKIs) treatment in patients with NSCLC. METHODS: Seven patients were prospectively enrolled who have pathologically-proven NSCLC with EGFR mutations or at least 2 of the following factors; adenocarcinoma, female, or never-smokers. Patients were treated with gefitinib or erlotinib and the start of chemotherapy was denoted day 0. DCE-MRI was performed at day-1, day+7, and day+28. Longitudinal changes of perfusion parameters were quantified and compared to Response Evaluation Criteria in Solid Tumors (RECIST) results. RESULTS: Quantitative perfusion parameters; Ktrans, ve and vp of the lung cancer showed a significant decrease at day+7 (P=0.016), but no further significant decrease between day+7 and day+28 (P>0.05). Semiquantitative markers for tumor enhancement curve pattern; EA (enhancement amplitude), MS (maximum slope), and AUC (area under the curve) also showed a significant decrease at day+7 (P=0.016, 0.031, and 0.016, respectively), but no further significant decrease between day+7 and day+28 (P>0.05). When RECIST applied, all patient was in the stable disease at day+7 and three patients showed partial response (PR) at day+28. All seven patients showed PR by the 3-month follow-up. CONCLUSIONS: Perfusion parameters may be used as an early non-invasive imaging biomarker for the response evaluation of target agent treatment in NSCLC.

Erratum: Multidetector CT Findings and Differential Diagnoses of Malignant Pleural Mesothelioma and Metastatic Pleural Diseases in Korea.

[This corrects the article on p. 545 in vol. 17, PMID: 27390546.].

Multidetector CT Findings and Differential Diagnoses of Malignant Pleural Mesothelioma and Metastatic Pleural Diseases in Korea.

OBJECTIVE: To compare the multidetector CT (MDCT) features of malignant pleural mesothelioma (MPM) and metastatic pleural disease (MPD). MATERIALS AND METHODS: The authors reviewed the MDCT images of 167 patients, 103 patients with MPM and 64 patients with MPD. All 167 cases were pathologically confirmed by sonography-guided needle biopsy of pleura, thoracoscopic pleural biopsy, or open thoracotomy. CT features were evaluated with respect to pleural effusion, pleural thickening, invasion of other organs, lung abnormality, lymphadenopathy, mediastinal shifting, thoracic volume decrease, asbestosis, and the presence of pleural plaque. RESULTS: Pleural thickening was the most common CT finding in MPM (96.1%) and MPD (93.8%). Circumferential pleural thickening (31.1% vs. 10.9%, odds ratio [OR] 3.670), thickening of fissural pleura (83.5% vs. 67.2%, OR 2.471), thickening of diaphragmatic pleura (90.3% vs. 73.4%, OR 3.364), pleural mass (38.8% vs. 23.4%, OR 2.074), pericardial involvement (56.3% vs. 20.3%, OR 5.056), and pleural plaque (66.0% vs. 21.9%, OR 6.939) were more frequently seen in MPM than in MPD. On the other hand, nodular pleural thickening (59.2% vs. 76.6%, OR 0.445), hilar lymph node metastasis (5.8% vs. 20.3%, OR 0.243), mediastinal lymph node metastasis (10.7% vs. 37.5%, OR 0.199), and hematogenous lung metastasis (9.7% vs. 29.2%, OR 0.261) were less frequent in MPM than in MPD. When we analyzed MPD from extrathoracic malignancy (EMPD) separately and compared them to MPM, circumferential pleural thickening, thickening of interlobar fissure, pericardial involvement and presence of pleural plaque were significant findings indicating MPM than EMPD. MPM had significantly lower occurrence of hematogenous lung metastasis, as compared with EMPD. CONCLUSION: Awareness of frequent and infrequent CT findings could aid in distinguishing MPM from MPD.

Changes in the flow-volume curve according to the degree of stenosis in patients with unilateral main bronchial stenosis.

OBJECTIVES: The shape of the flow-volume (F-V) curve is known to change to showing a prominent plateau as stenosis progresses in patients with tracheal stenosis. However, no study has evaluated changes in the F-V curve according to the degree of bronchial stenosis in patients with unilateral main bronchial stenosis. METHODS: We performed an analysis of F-V curves in 29 patients with unilateral bronchial stenosis with the aid of a graphic digitizer between January 2005 and December 2011. RESULTS: The primary diseases causing unilateral main bronchial stenosis were endobronchial tuberculosis (86%), followed by benign bronchial tumor (10%), and carcinoid (3%). All unilateral main bronchial stenoses were classified into one of five grades (I, ≤25%; II, 26%-50%; III, 51%-75%; IV, 76%-90%; V, >90% to near-complete obstruction without ipsilateral lung collapse). A monophasic F-V curve was observed in patients with grade I stenosis and biphasic curves were observed for grade II-IV stenosis. Both monophasic (81%) and biphasic shapes (18%) were observed in grade V stenosis. After standardization of the biphasic shape of the F-V curve, the breakpoints of the biphasic curve moved in the direction of high volume (x-axis) and low flow (y-axis) according to the progression of stenosis. CONCLUSION: In unilateral bronchial stenosis, a biphasic F-V curve appeared when bronchial stenosis was >25% and disappeared when obstruction was near complete. In addition, the breakpoint moved in the direction of high volume and low flow with the progression of stenosis.

Low-dose CT screening in an Asian population with diverse risk for lung cancer: A retrospective cohort study.

OBJECTIVES: To evaluate the performance of low-dose CT (LDCT) screening for lung cancer (LCA) detection in an Asian population with diverse risks for LCA. MATERIALS AND METHODS: LCA screening was performed in 12,427 symptomless Asian subjects using either LDCT (5,771) or chest radiography (CXR) (6,656) in a non-trial setting. Subjects were divided into high-risk and non-high-risk groups. Data were collected on the number of patients with screening-detected LCAs and their survival in order to compare outcomes between LDCT and CXR screening with the stratification of risks considering age, sex and smoking status. RESULTS: In the non-high-risk group, a significant difference was observed for the detection of lung cancer (adjusted OR, 5.07; 95 % CI, 2.72-9.45) and survival (adjusted HR of LCA survival between LDCT vs. CXR group, 0.08; 95 % CI, 0.01-0.62). No difference in detection or survival of LCA was noticed in the high-risk group. LCAs in the non-high-risk group were predominantly adenocarcinomas (96 %), and more likely to be part-solid or non-solid compared with those in the high-risk group (p = 0.023). CONCLUSIONS: In the non-high-risk group, LDCT helps detect more LCAs and offers better survival than CXR screening, due to better detection of part solid or non-solid lung adenocarcinomas. KEY POINTS: • In an Asian non-high-risk group, LDCT helps detect more early-staged LCAs. • CT-detected lung cancers in non-high-risk subjects demonstrate better survival than CXR-detected cancers. • CT-detected lung cancers in non-high-risk subjects are predominantly part-solid or non-solid adenocarcinomas. • Mortality benefit of LDCT screening in non-high-risk subjects needs to be investigated.

Semiautomatic determination of arterial input functions for quantitative dynamic contrast-enhanced magnetic resonance imaging in non-small cell lung cancer patients.

OBJECTIVES: The aim of this study was to validate a semiautomatic detection method for the arterial input functions (AIFs) using Kendall coefficient of concordance (KCC) for quantitative analysis of dynamic contrast-enhanced magnetic resonance imaging in non-small cell lung cancer patients. MATERIALS AND METHODS: We prospectively enrolled 28 patients (17 men, 11 women; mean age, 62 years) who had biopsy-proven non-small cell lung cancer. All enrolled patients underwent dynamic contrast-enhanced magnetic resonance imaging of the entire thorax. For the quantitative measurement of pharmacokinetic parameters, K and ve, of the lung cancers, AIFs were determined in 2 different ways: a manual method that involved 3 independent thoracic radiologists selecting a region of interest (ROI) within the aortic arch in the 2D coronal plane and a semiautomatic method that used in-house software to establish a KCC score, which provided a measure of similarity to typical AIF pattern. Three independent readers selected voxel clusters with high KCC scores calculated 3-dimensionally across planes in the data set. K and ve were correlated using intraclass correlation coefficients (ICCs), and Bland-Altman plots were used to examine agreement across methods and reproducibility within a method. RESULTS: Arterial input functions were determined using the data from ROI volumes that were significantly larger in the semiautomatic method (mean ± SD, 3360 ± 768 mm) than in the manual method (677 ± 380 mm) (P < 0.001). K showed very strong agreement (ICC, 0.927) and ve showed moderately strong agreement (ICC, 0.718) between the semiautomatic and manual methods. The reproducibility for K (ICCmanual, 0.813 and ICCsemiautomatic, 0.998; P < 0.001) and ve (ICCmanual, 0.455 and ICCsemiautomatic, 0.985, P < 0.001) was significantly better with the semiautomatic method than the manual method. CONCLUSION: We found semiautomated detection using KCC to be a robust method for determining the AIF. This method allows for larger ROIs specified in 3D across planes as opposed to manually selected ROIs restricted to the 2D coronal images seen by the reader and provides increased reproducibility that is comparable with manual specification.

Extrapulmonary lymphangioleiomyoma: clinicopathological analysis of 4 cases.

BACKGROUND: Lymphangioleiomyomatosis (LAM) is a slowly progressive neoplastic disease that predominantly affects females. Usually, LAM affects the lung; it can also affect extrapulmonary sites, such as the mediastinum, the retroperitoneum, or the lymph nodes, although these locations are rare. A localized form of LAM can manifest as extrapulmonary lesions; this form is referred to as extrapulmonary lymphangioleiomyoma (E-LAM). Due to the rare occurrence of E-LAM and its variable, atypical location, E-LAM is often difficult to diagnose. Herein, we report the clinicopathological information from four E-LAM cases, and also review previous articles investigating this disease. METHODS: Four patients with E-LAM were identified at the Samsung Medical Center (Seoul, Korea) from 1995 to 2012. All E-LAM lesions underwent surgical excision. RESULTS: All patients were females within the age range of 43 to 47 years. Two patients had para-aortic retroperitoneal masses, while the other two patients had pelvic lesions; two out of the four patients also had accompanying pulmonary LAM. In addition, no patient displayed any evidence of tuberous sclerosis. Histologically, two patients exhibited nuclear atypism with cytologic degeneration. CONCLUSIONS: E-LAM should be considered in the differential diagnosis of patients presenting with pelvic or para-aortic masses. We also conclude that further clinical and pathological evaluation is needed in patients with E-LAM and nuclear atypism.

Subcentimeter lung nodules stable for 2 years at LDCT: long-term follow-up using volumetry.

BACKGROUND AND OBJECTIVE: Subcentimeter nodules without change in size during long-term follow-up period (for minimum 2 years) are assumed as benign lesions. However, the 2-year stability rule has not been fully verified so far and is still questionable. Thus, we aimed to retrospectively investigate long-term follow-up results for 2-year stable subcentimeter nodules at screening low-dose computed tomography (LDCT). METHODS: A total of 635 subjects having had follow-up LDCTs for the initial 2-year screening period and additional 3 years thereafter and having had non-calcified subcentimeter nodules were included. By using computed tomography (CT) nodule volumetry software, we measured interval changes in nodule volume. RESULTS: A total of 1107 subcentimeter nodules (1037 solid, 70 ground-glass opacity nodules (GGNs)) were detected at baseline CT. Of 1037 solid nodules, 1032 showed no growth during the initial 2-year and 5-year follow-up period. Fifty-nine GGNs were stable for initial 2 years, but two (3.4%) were later proved as adenocarcinomas. Among five solid nodules that showed growth during the initial 2-year follow-up period, one (20%) proved to be an adenocarcinoma, whereas four (36.4%) of 11 GGNs that demonstrated growth were diagnosed as lung cancers. CONCLUSIONS: All solid subcentimeter nodules having initial 2-year stability at screening LDCT can be considered benign because none shows growth at further follow-up CT. On the other hand, subcentimeter GGNs have more chance of growth than solid nodules and need further follow-up CT for more than 2 years.

Diffusion-weighted MRI for distinguishing non-neoplastic cysts from solid masses in the mediastinum: problem-solving in mediastinal masses of indeterminate internal characteristics on CT.

OBJECTIVES: To evaluate the usefulness of diffusion-weighted (DW) magnetic resonance images for distinguishing non-neoplastic cysts from solid masses of indeterminate internal characteristics on computed tomography (CT) in the mediastinum. METHODS: We enrolled 25 patients with pathologically proved mediastinal masses who underwent both thoracic CT and magnetic resonance imaging (MRI) including diffusion-weighted imaging (DWI). MRI was performed in patients with mediastinal masses of indeterminate internal characteristics on CT. Two thoracic radiologists evaluated the morphological features and quantitatively measured the net enhancement of the masses at CT. They also reviewed MR images including unenhanced T1- and T2-weighted images, gadolinium-enhanced images and DW images. RESULTS: The enrolled patients had 15 solid masses and ten non-neoplastic cysts. Although the morphological features and the extent of enhancement on CT did not differ significantly between solid and cystic masses in the mediastinum (P > 0.05), non-neoplastic cysts were distinguishable from solid masses by showing signal suppression on high-b-value DW images or high apparent diffusion coefficient (ADC) values of more than 2.5 × 10(-3) mm(2)/s (P < 0.001). ADC values of non-neoplastic cysts (3.67 ± 0.87 × 10(-3) mm(2)/s) were significantly higher than that of solid masses (1.46 ± 0.50 × 10(-3) mm(2)/s) (P < 0.001). CONCLUSIONS: DWI can help differentiate solid and cystic masses in the mediastinum, even when CT findings are questionable. KEY POINTS: • Non-invasive diagnosis of non-neoplastic cysts can save surgical biopsy or excision. • Conventional CT or MRI findings cannot always provide a confident diagnosis. • Mediastinal masses can be well-characterised with DWI. • Non-neoplastic mediastinal cysts show significantly higher ADC values than cystic tumours. • DWI is useful to determine treatment strategy.

Histopathology of lung adenocarcinoma based on new IASLC/ATS/ERS classification: prognostic stratification with functional and metabolic imaging biomarkers.

PURPOSE: To correlate the results of histopathologic subtyping and grading of lung adenocarcinoma with maximum standardized uptake values (SUVmax) on positron emission tomography (PET)/computed tomography and apparent diffusion coefficient (ADC) values on diffusion-weighted MRI (DWI). MATERIALS AND METHODS: Forty-three patients were included. The SUVmax and mean ADC values of tumors were measured and correlated with the histologic subtypes and grades of lung adenocarcinomas based on the IASLC/ATS/ERS classification scheme. Disease-free survival (DFS) was estimated by using the Kaplan-Meier method, and the log-rank test was used to evaluate differences among three histologic grades or subgroups classified with imaging biomarker study results. RESULTS: Five (12.5%) tumors belonged to low grade, 30 (70%) to intermediate grade, and 8 (18.5%) to high grade, and patients with low-grade histology had lower risk of recurrence than those with intermediate- or high-grade histology (P = 0.048). A significant difference in SUVmax and mean ADC values was observed among three histologic grades (Ps < 0.001). Regarding DFS, lower metabolic (PET) activity or higher functional (DWI) diffusivity showed longer DFS. When patients (n = 30; 70% of patients) with intermediate histologic grade were subgrouped in consideration of both SUVmax and mean ADC results, combining metabolic and functional criteria helped stratify patients more precisely (P = 0.006). CONCLUSION: SUVmax and mean ADC value correlate well with the histologic grades in lung adenocarcinomas, and combining both imaging biomarker study results leads to more useful stratification of patients into different prognostic subsets than the results of each study.

Persistent pure ground-glass opacity lung nodules ≥ 10 mm in diameter at CT scan: histopathologic comparisons and prognostic implications.

BACKGROUND: Little is known about the histopathology and prognosis of persistent pure ground-glass opacity nodules (GGNs) of ≥ 10 mm in diameter. We aimed to compare the morphologic features of persistent pure GGNs of ≥ 10 mm in diameter at thin-section CT (TSCT) scan with histopathology and patient prognosis. METHODS: A total of 46 resected GGNs that were evaluated with TSCT scan and followed up for ≥ 3 years were included in this study. Correlations between histopathology (adenocarcinoma in situ [AIS], minimally invasive adenocarcinoma [MIA], and invasive adenocarcinoma) and CT scan characteristics were examined. CT scan and clinicodemographic data were investigated by univariate and multivariate analyses to identify features that helped distinguish invasive adenocarcinoma from AIS or MIA. Disease recurrence was also evaluated. RESULTS: The nodules included 19 AISs (41%), nine MIAs (20%), and 18 invasive adenocarcinomas (39%). On univariate analysis, the presence of air bronchogram (P = .012), size of nodule (P = .032, cutoff = 16.4 mm in diameter), and mass of nodule (P = .040, cutoff = 0.472 g) were significant factors that differentiated invasive adenocarcinoma from AIS or MIA. On multivariate analysis, size (P = .010) and mass of nodule (P = .016) were significant determinants for invasive adenocarcinoma. There were no cases of recurrence during a follow-up period of ≥ 3 years after surgical resection. CONCLUSIONS: In persistent pure GGNs of ≥ 10 mm in diameter, the size and mass of the nodule are determinants of invasive adenocarcinoma, for which surgical resection leads to excellent prognosis.

A case of acute pulmonary embolism associated with dysplasminogenemia.

The incidence of pulmonary embolism (PE) rises markedly with age, and only a few cases have been reported in younger adults. Thrombophilia has been reported as one of the predisposing factors for PE in younger adults. Here we report an extraordinary case of PE complicated with dysplasminogenemia, a rare genetic disorder resulting in hypercoagulability, in a young male. An 18-yr-old male visited an emergency room in the United States complaining chest discomfort. He was diagnosed as PE with deep vein thrombosis without apparent risk factors. Anticoagulation therapy with warfarin had been initiated and discontinued after 6 months of treatment. After returning to Korea he was tested for thrombophilia which revealed decreased activity of plasminogen and subsequent analysis of PLG gene showed heterozygous Ala620Thr mutation. He was diagnosed with PE complicated with dysplasminogenemia. Life-long anticoagulation therapy was initiated. He is currently under follow-up without clinical events for 2 yr.

Coregistered whole body magnetic resonance imaging-positron emission tomography (MRI-PET) versus PET-computed tomography plus brain MRI in staging resectable lung cancer: comparisons of clinical effectiveness in a randomized trial.

BACKGROUND: The objective of this study was to assess whether coregistered whole brain (WB) magnetic resonance imaging-positron emission tomography (MRI-PET) would increase the number of correctly upstaged patients compared with WB PET-computed tomography (PET-CT) plus dedicated brain MRI in patients with nonsmall cell lung cancer (NSCLC). METHODS: From January 2010 through November 2011, patients with NSCLC who had resectable disease based on conventional staging were assigned randomly either to coregistered MRI-PET or WB PET-CT plus brain MRI (ClinicalTrials.gov trial NCT01065415). The primary endpoint was correct upstaging (the identification of lesions with higher tumor, lymph node, or metastasis classification, verified with biopsy or other diagnostic test) to have the advantage of avoiding unnecessary thoracotomy, to determine appropriate treatment, and to accurately predict patient prognosis. The secondary endpoints were over staging and under staging compared with pathologic staging. RESULTS: Lung cancer was correctly upstaged in 37 of 143 patients (25.9%) in the MRI-PET group and in 26 of 120 patients (21.7%) in the PET-CT plus brain MRI group (4.2% difference; 95% confidence interval, -6.1% to 14.5%; P = .426). Lung cancer was over staged in 26 of 143 patients (18.2%) in the MRI-PET group and in 7 of 120 patients (5.8%) in the PET-CT plus brain MRI group (12.4% difference; 95% confidence interval, 4.8%-20%; P = .003), whereas lung cancer was under staged in 18 of 143 patients (12.6%) and in 28 of 120 patients (23.3%), respectively (-10.7% difference; 95% confidence interval, -20.1% to -1.4%; P = .022). CONCLUSIONS: Although both staging tools allowed greater than 20% correct upstaging compared with conventional staging methods, coregistered MRI-PET did not appear to help identify significantly more correctly upstaged patients than PET-CT plus brain MRI in patients with NSCLC.

Dual-energy CT in patients treated with anti-angiogenic agents for non-small cell lung cancer: new method of monitoring tumor response?

OBJECTIVE: To evaluate tumor responses in patients treated with anti-angiogenic agents for non-small cell lung cancer (NSCLC) by assessing intratumoral changes using a dual-energy CT (DECT) (based on Choi's criteria) and to compare it to traditional Response Evaluation Criteria in Solid Tumors (RECIST) criteria. MATERIALS AND METHODS: Ten NSCLC patients treated with bevacizumab underwent DECT. Tumor responses to anti-angiogenic therapy were assessed and compared with the baseline CT results using both RECIST (size changes only) and Choi's criteria (reflecting net tumor enhancement). Kappa statistics was used to evaluate agreements between tumor responses assessed by RECIST and Choi's criteria. RESULTS: The weighted κ value for the comparison of tumor responses between the RECIST and Choi's criteria was 0.72. Of 31 target lesions (21 solid nodules, 8 lymph nodes, and two ground-glass opacity nodules [GGNs]), five lesions (16%) showed discordant responses between RECIST and Choi's criteria. Iodine-enhanced images allowed for a distinction between tumor enhancement and hemorrhagic response (detected in 14% [4 of 29, excluding GGNs] of target lesions on virtual nonenhanced images). CONCLUSION: DECT may serve as a useful tool for response evaluation after anti-angiogenic treatment in NSCLC patients by providing information on the net enhancement of target lesions without obtaining non-enhanced images.